Washington University AI Blood Test Distinguishes Four Dementia-Related Brain Diseases

Researchers at Washington University School of Medicine in St. Louis have created an artificial‑intelligence classifier that identifies four major neurodegenerative conditions—Alzheimer’s disease, Parkinson’s disease, frontotemporal dementia and dementia with Lewy bodies—and separates them from normal brain aging. Using a panel of 15 blood‑based proteins, the model was trained on data from more than 3,200 participants and achieved an overall diagnostic accuracy of 92.3%, correctly detecting mixed pathology in patients where multiple diseases co‑occur.

The classifier’s predictions were validated on a separate set of 225 individuals with post‑mortem brain examinations, showing strong alignment with actual pathological burden. Lead author Carlos Cruchaga said, “Our goal was to build a test that doesn’t just say ‘yes’ or ‘no’ to one disease but instead gives an indication of all the major neurodegenerative diseases happening in that person.” The test is still experimental and requires further validation in larger, more diverse populations before clinical use.